add some chapter exercices
This commit is contained in:
tsb1995
parent
ce2759452b
commit
e80eae2468
|
|
@ -0,0 +1,437 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Exercise 12**\n",
|
||||
"\n",
|
||||
"Implement batch gradient descent from scratch (no SKLearn!)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"import os\n",
|
||||
"from matplotlib import pyplot as plt\n",
|
||||
"from sklearn import datasets\n",
|
||||
"\n",
|
||||
"%matplotlib inline"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"['data', 'target', 'target_names', 'DESCR', 'feature_names', 'filename']"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"iris = datasets.load_iris()\n",
|
||||
"list(iris.keys())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
".. _iris_dataset:\n",
|
||||
"\n",
|
||||
"Iris plants dataset\n",
|
||||
"--------------------\n",
|
||||
"\n",
|
||||
"**Data Set Characteristics:**\n",
|
||||
"\n",
|
||||
" :Number of Instances: 150 (50 in each of three classes)\n",
|
||||
" :Number of Attributes: 4 numeric, predictive attributes and the class\n",
|
||||
" :Attribute Information:\n",
|
||||
" - sepal length in cm\n",
|
||||
" - sepal width in cm\n",
|
||||
" - petal length in cm\n",
|
||||
" - petal width in cm\n",
|
||||
" - class:\n",
|
||||
" - Iris-Setosa\n",
|
||||
" - Iris-Versicolour\n",
|
||||
" - Iris-Virginica\n",
|
||||
" \n",
|
||||
" :Summary Statistics:\n",
|
||||
"\n",
|
||||
" ============== ==== ==== ======= ===== ====================\n",
|
||||
" Min Max Mean SD Class Correlation\n",
|
||||
" ============== ==== ==== ======= ===== ====================\n",
|
||||
" sepal length: 4.3 7.9 5.84 0.83 0.7826\n",
|
||||
" sepal width: 2.0 4.4 3.05 0.43 -0.4194\n",
|
||||
" petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)\n",
|
||||
" petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)\n",
|
||||
" ============== ==== ==== ======= ===== ====================\n",
|
||||
"\n",
|
||||
" :Missing Attribute Values: None\n",
|
||||
" :Class Distribution: 33.3% for each of 3 classes.\n",
|
||||
" :Creator: R.A. Fisher\n",
|
||||
" :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\n",
|
||||
" :Date: July, 1988\n",
|
||||
"\n",
|
||||
"The famous Iris database, first used by Sir R.A. Fisher. The dataset is taken\n",
|
||||
"from Fisher's paper. Note that it's the same as in R, but not as in the UCI\n",
|
||||
"Machine Learning Repository, which has two wrong data points.\n",
|
||||
"\n",
|
||||
"This is perhaps the best known database to be found in the\n",
|
||||
"pattern recognition literature. Fisher's paper is a classic in the field and\n",
|
||||
"is referenced frequently to this day. (See Duda & Hart, for example.) The\n",
|
||||
"data set contains 3 classes of 50 instances each, where each class refers to a\n",
|
||||
"type of iris plant. One class is linearly separable from the other 2; the\n",
|
||||
"latter are NOT linearly separable from each other.\n",
|
||||
"\n",
|
||||
".. topic:: References\n",
|
||||
"\n",
|
||||
" - Fisher, R.A. \"The use of multiple measurements in taxonomic problems\"\n",
|
||||
" Annual Eugenics, 7, Part II, 179-188 (1936); also in \"Contributions to\n",
|
||||
" Mathematical Statistics\" (John Wiley, NY, 1950).\n",
|
||||
" - Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.\n",
|
||||
" (Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.\n",
|
||||
" - Dasarathy, B.V. (1980) \"Nosing Around the Neighborhood: A New System\n",
|
||||
" Structure and Classification Rule for Recognition in Partially Exposed\n",
|
||||
" Environments\". IEEE Transactions on Pattern Analysis and Machine\n",
|
||||
" Intelligence, Vol. PAMI-2, No. 1, 67-71.\n",
|
||||
" - Gates, G.W. (1972) \"The Reduced Nearest Neighbor Rule\". IEEE Transactions\n",
|
||||
" on Information Theory, May 1972, 431-433.\n",
|
||||
" - See also: 1988 MLC Proceedings, 54-64. Cheeseman et al\"s AUTOCLASS II\n",
|
||||
" conceptual clustering system finds 3 classes in the data.\n",
|
||||
" - Many, many more ...\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(iris.DESCR)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X = iris[\"data\"][:, (2,3)] # petal length and width\n",
|
||||
"y = (iris[\"target\"]) # 1 if Iris virginica, else 0"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(150, 2)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Important variables\n",
|
||||
"\n",
|
||||
"X_with_bias = np.c_[np.ones([len(X), 1]), X] # Add column of ones for theta intercept term\n",
|
||||
"alpha = 0.1\n",
|
||||
"iterations=1500\n",
|
||||
"\n",
|
||||
"print(X.shape)\n",
|
||||
"\n",
|
||||
"# NOTE: If ValueError: all input arrays must have the same shape appears then you may have run this cel multiple times\n",
|
||||
"# which will have added multiple collumns of ones to the matrix X"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 70,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Setup our proportions\n",
|
||||
"\n",
|
||||
"test_ratio = .2\n",
|
||||
"val_ratio = .2\n",
|
||||
"total_size = len(X)\n",
|
||||
"\n",
|
||||
"# Calculate size of our splits\n",
|
||||
"\n",
|
||||
"test_size = int(test_ratio*total_size)\n",
|
||||
"val_size = int(val_ratio*total_size)\n",
|
||||
"train_size = total_size - test_size - val_size\n",
|
||||
"\n",
|
||||
"# Split our data\n",
|
||||
"\n",
|
||||
"rnd_indices = np.random.permutation(total_size) # Shuffle our input matrix\n",
|
||||
"\n",
|
||||
"X_train = X_with_bias[rnd_indices[:train_size]]\n",
|
||||
"y_train = y[rnd_indices[:train_size]]\n",
|
||||
"X_valid = X_with_bias[rnd_indices[train_size:-test_size]]\n",
|
||||
"y_valid = y[rnd_indices[train_size:-test_size]]\n",
|
||||
"X_test = X_with_bias[rnd_indices[-test_size:]]\n",
|
||||
"y_test = y[rnd_indices[-test_size:]]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 71,
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(90, 3)\n",
|
||||
"(30, 2)\n",
|
||||
"(30, 3)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(X_train.shape)\n",
|
||||
"print(X_val.shape)\n",
|
||||
"print(X_test.shape)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 72,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def to_one_hot(y):\n",
|
||||
" n_classes = y.max() + 1\n",
|
||||
" m = len(y)\n",
|
||||
" Y_one_hot = np.zeros((m, n_classes)) # Setup zero matrix with m rows and a column for each class\n",
|
||||
" Y_one_hot[np.arange(m), y] = 1 # Fill in ones\n",
|
||||
" return Y_one_hot"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 73,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"array([2, 2, 2, 0, 0, 0, 1, 2, 0, 2])"
|
||||
]
|
||||
},
|
||||
"execution_count": 73,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"y_train[:10]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 74,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"array([[0., 0., 1.],\n",
|
||||
" [0., 0., 1.],\n",
|
||||
" [0., 0., 1.],\n",
|
||||
" [1., 0., 0.],\n",
|
||||
" [1., 0., 0.],\n",
|
||||
" [1., 0., 0.],\n",
|
||||
" [0., 1., 0.],\n",
|
||||
" [0., 0., 1.],\n",
|
||||
" [1., 0., 0.],\n",
|
||||
" [0., 0., 1.]])"
|
||||
]
|
||||
},
|
||||
"execution_count": 74,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"to_one_hot(y_train[:10])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 75,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"Y_train_one_hot = to_one_hot(y_train)\n",
|
||||
"Y_test_one_hot = to_one_hot(y_test)\n",
|
||||
"Y_val_one_hot = to_one_hot(y_val)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 76,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Softmax function = exp(X) / (sum of exp(X))\n",
|
||||
"\n",
|
||||
"def softmax(logits):\n",
|
||||
" exps = np.exp(logits)\n",
|
||||
" exp_sums = np.sum(exps, axis=1, keepdims=True)\n",
|
||||
" return exps / exp_sums"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 82,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_inputs = X_train.shape[1] # Number of features\n",
|
||||
"n_outputs = len(np.unique(y_train)) # 3 uniqure values which will each be a possible output"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 80,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"0 1.4567897105648775\n",
|
||||
"500 0.7451993577978241\n",
|
||||
"1000 0.6279369677273878\n",
|
||||
"1500 0.5572702696067121\n",
|
||||
"2000 0.5111859948576022\n",
|
||||
"2500 0.47856473219026296\n",
|
||||
"3000 0.45387932862540925\n",
|
||||
"3500 0.43422780377165426\n",
|
||||
"4000 0.41797875623202274\n",
|
||||
"4500 0.4041537521442775\n",
|
||||
"5000 0.39213163561158126\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"eta = 0.01\n",
|
||||
"n_iterations = 5001\n",
|
||||
"m = len(X_train)\n",
|
||||
"epsilon = 1e-7\n",
|
||||
"\n",
|
||||
"Theta = np.random.randn(n_inputs, n_outputs)\n",
|
||||
"\n",
|
||||
"# Cycle through set to apply batch gradient descent\n",
|
||||
"\n",
|
||||
"for iteration in range(n_iterations):\n",
|
||||
" logits = X_train.dot(Theta) # Logits which are raw predictions from applying X to Theta\n",
|
||||
" p_hat = softmax(logits) # Apply softmax to logits to get our probabilities\n",
|
||||
" loss = -np.mean(np.sum(Y_train_one_hot * np.log(p_hat + epsilon), axis=1)) # Compute loss function\n",
|
||||
" error = p_hat - Y_train_one_hot # Compute error \n",
|
||||
" if iteration % 500 == 0:\n",
|
||||
" print(iteration, loss)\n",
|
||||
" Grad = 1/m * X_train.T.dot(error)\n",
|
||||
" Theta = Theta - eta * Grad\n",
|
||||
" "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 81,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"array([[ 3.61613128, 0.06856255, -2.86225561],\n",
|
||||
" [-0.2597962 , 0.80558911, 0.70553675],\n",
|
||||
" [-0.90831271, 0.18903751, 2.43558706]])"
|
||||
]
|
||||
},
|
||||
"execution_count": 81,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"Theta"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 87,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.9666666666666667"
|
||||
]
|
||||
},
|
||||
"execution_count": 87,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Predictions\n",
|
||||
"\n",
|
||||
"logits = X_valid.dot(Theta)\n",
|
||||
"p_hat = softmax(logits)\n",
|
||||
"y_pred = np.argmax(p_hat, axis=1)\n",
|
||||
"\n",
|
||||
"accuracy_score = np.mean(y_pred == y_valid)\n",
|
||||
"accuracy_score"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
|
|
@ -0,0 +1,97 @@
|
|||
6.1101,17.592
|
||||
5.5277,9.1302
|
||||
8.5186,13.662
|
||||
7.0032,11.854
|
||||
5.8598,6.8233
|
||||
8.3829,11.886
|
||||
7.4764,4.3483
|
||||
8.5781,12
|
||||
6.4862,6.5987
|
||||
5.0546,3.8166
|
||||
5.7107,3.2522
|
||||
14.164,15.505
|
||||
5.734,3.1551
|
||||
8.4084,7.2258
|
||||
5.6407,0.71618
|
||||
5.3794,3.5129
|
||||
6.3654,5.3048
|
||||
5.1301,0.56077
|
||||
6.4296,3.6518
|
||||
7.0708,5.3893
|
||||
6.1891,3.1386
|
||||
20.27,21.767
|
||||
5.4901,4.263
|
||||
6.3261,5.1875
|
||||
5.5649,3.0825
|
||||
18.945,22.638
|
||||
12.828,13.501
|
||||
10.957,7.0467
|
||||
13.176,14.692
|
||||
22.203,24.147
|
||||
5.2524,-1.22
|
||||
6.5894,5.9966
|
||||
9.2482,12.134
|
||||
5.8918,1.8495
|
||||
8.2111,6.5426
|
||||
7.9334,4.5623
|
||||
8.0959,4.1164
|
||||
5.6063,3.3928
|
||||
12.836,10.117
|
||||
6.3534,5.4974
|
||||
5.4069,0.55657
|
||||
6.8825,3.9115
|
||||
11.708,5.3854
|
||||
5.7737,2.4406
|
||||
7.8247,6.7318
|
||||
7.0931,1.0463
|
||||
5.0702,5.1337
|
||||
5.8014,1.844
|
||||
11.7,8.0043
|
||||
5.5416,1.0179
|
||||
7.5402,6.7504
|
||||
5.3077,1.8396
|
||||
7.4239,4.2885
|
||||
7.6031,4.9981
|
||||
6.3328,1.4233
|
||||
6.3589,-1.4211
|
||||
6.2742,2.4756
|
||||
5.6397,4.6042
|
||||
9.3102,3.9624
|
||||
9.4536,5.4141
|
||||
8.8254,5.1694
|
||||
5.1793,-0.74279
|
||||
21.279,17.929
|
||||
14.908,12.054
|
||||
18.959,17.054
|
||||
7.2182,4.8852
|
||||
8.2951,5.7442
|
||||
10.236,7.7754
|
||||
5.4994,1.0173
|
||||
20.341,20.992
|
||||
10.136,6.6799
|
||||
7.3345,4.0259
|
||||
6.0062,1.2784
|
||||
7.2259,3.3411
|
||||
5.0269,-2.6807
|
||||
6.5479,0.29678
|
||||
7.5386,3.8845
|
||||
5.0365,5.7014
|
||||
10.274,6.7526
|
||||
5.1077,2.0576
|
||||
5.7292,0.47953
|
||||
5.1884,0.20421
|
||||
6.3557,0.67861
|
||||
9.7687,7.5435
|
||||
6.5159,5.3436
|
||||
8.5172,4.2415
|
||||
9.1802,6.7981
|
||||
6.002,0.92695
|
||||
5.5204,0.152
|
||||
5.0594,2.8214
|
||||
5.7077,1.8451
|
||||
7.6366,4.2959
|
||||
5.8707,7.2029
|
||||
5.3054,1.9869
|
||||
8.2934,0.14454
|
||||
13.394,9.0551
|
||||
5.4369,0.61705
|
||||
|
|
@ -0,0 +1,47 @@
|
|||
2104,3,399900
|
||||
1600,3,329900
|
||||
2400,3,369000
|
||||
1416,2,232000
|
||||
3000,4,539900
|
||||
1985,4,299900
|
||||
1534,3,314900
|
||||
1427,3,198999
|
||||
1380,3,212000
|
||||
1494,3,242500
|
||||
1940,4,239999
|
||||
2000,3,347000
|
||||
1890,3,329999
|
||||
4478,5,699900
|
||||
1268,3,259900
|
||||
2300,4,449900
|
||||
1320,2,299900
|
||||
1236,3,199900
|
||||
2609,4,499998
|
||||
3031,4,599000
|
||||
1767,3,252900
|
||||
1888,2,255000
|
||||
1604,3,242900
|
||||
1962,4,259900
|
||||
3890,3,573900
|
||||
1100,3,249900
|
||||
1458,3,464500
|
||||
2526,3,469000
|
||||
2200,3,475000
|
||||
2637,3,299900
|
||||
1839,2,349900
|
||||
1000,1,169900
|
||||
2040,4,314900
|
||||
3137,3,579900
|
||||
1811,4,285900
|
||||
1437,3,249900
|
||||
1239,3,229900
|
||||
2132,4,345000
|
||||
4215,4,549000
|
||||
2162,4,287000
|
||||
1664,2,368500
|
||||
2238,3,329900
|
||||
2567,4,314000
|
||||
1200,3,299000
|
||||
852,2,179900
|
||||
1852,4,299900
|
||||
1203,3,239500
|
||||
|
|
@ -0,0 +1,437 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Exercise 12**\n",
|
||||
"\n",
|
||||
"Implement batch gradient descent from scratch (no SKLearn!)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"import os\n",
|
||||
"from matplotlib import pyplot as plt\n",
|
||||
"from sklearn import datasets\n",
|
||||
"\n",
|
||||
"%matplotlib inline"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"['data', 'target', 'target_names', 'DESCR', 'feature_names', 'filename']"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"iris = datasets.load_iris()\n",
|
||||
"list(iris.keys())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
".. _iris_dataset:\n",
|
||||
"\n",
|
||||
"Iris plants dataset\n",
|
||||
"--------------------\n",
|
||||
"\n",
|
||||
"**Data Set Characteristics:**\n",
|
||||
"\n",
|
||||
" :Number of Instances: 150 (50 in each of three classes)\n",
|
||||
" :Number of Attributes: 4 numeric, predictive attributes and the class\n",
|
||||
" :Attribute Information:\n",
|
||||
" - sepal length in cm\n",
|
||||
" - sepal width in cm\n",
|
||||
" - petal length in cm\n",
|
||||
" - petal width in cm\n",
|
||||
" - class:\n",
|
||||
" - Iris-Setosa\n",
|
||||
" - Iris-Versicolour\n",
|
||||
" - Iris-Virginica\n",
|
||||
" \n",
|
||||
" :Summary Statistics:\n",
|
||||
"\n",
|
||||
" ============== ==== ==== ======= ===== ====================\n",
|
||||
" Min Max Mean SD Class Correlation\n",
|
||||
" ============== ==== ==== ======= ===== ====================\n",
|
||||
" sepal length: 4.3 7.9 5.84 0.83 0.7826\n",
|
||||
" sepal width: 2.0 4.4 3.05 0.43 -0.4194\n",
|
||||
" petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)\n",
|
||||
" petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)\n",
|
||||
" ============== ==== ==== ======= ===== ====================\n",
|
||||
"\n",
|
||||
" :Missing Attribute Values: None\n",
|
||||
" :Class Distribution: 33.3% for each of 3 classes.\n",
|
||||
" :Creator: R.A. Fisher\n",
|
||||
" :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\n",
|
||||
" :Date: July, 1988\n",
|
||||
"\n",
|
||||
"The famous Iris database, first used by Sir R.A. Fisher. The dataset is taken\n",
|
||||
"from Fisher's paper. Note that it's the same as in R, but not as in the UCI\n",
|
||||
"Machine Learning Repository, which has two wrong data points.\n",
|
||||
"\n",
|
||||
"This is perhaps the best known database to be found in the\n",
|
||||
"pattern recognition literature. Fisher's paper is a classic in the field and\n",
|
||||
"is referenced frequently to this day. (See Duda & Hart, for example.) The\n",
|
||||
"data set contains 3 classes of 50 instances each, where each class refers to a\n",
|
||||
"type of iris plant. One class is linearly separable from the other 2; the\n",
|
||||
"latter are NOT linearly separable from each other.\n",
|
||||
"\n",
|
||||
".. topic:: References\n",
|
||||
"\n",
|
||||
" - Fisher, R.A. \"The use of multiple measurements in taxonomic problems\"\n",
|
||||
" Annual Eugenics, 7, Part II, 179-188 (1936); also in \"Contributions to\n",
|
||||
" Mathematical Statistics\" (John Wiley, NY, 1950).\n",
|
||||
" - Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.\n",
|
||||
" (Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.\n",
|
||||
" - Dasarathy, B.V. (1980) \"Nosing Around the Neighborhood: A New System\n",
|
||||
" Structure and Classification Rule for Recognition in Partially Exposed\n",
|
||||
" Environments\". IEEE Transactions on Pattern Analysis and Machine\n",
|
||||
" Intelligence, Vol. PAMI-2, No. 1, 67-71.\n",
|
||||
" - Gates, G.W. (1972) \"The Reduced Nearest Neighbor Rule\". IEEE Transactions\n",
|
||||
" on Information Theory, May 1972, 431-433.\n",
|
||||
" - See also: 1988 MLC Proceedings, 54-64. Cheeseman et al\"s AUTOCLASS II\n",
|
||||
" conceptual clustering system finds 3 classes in the data.\n",
|
||||
" - Many, many more ...\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(iris.DESCR)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X = iris[\"data\"][:, (2,3)] # petal length and width\n",
|
||||
"y = (iris[\"target\"]) # 1 if Iris virginica, else 0"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(150, 2)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Important variables\n",
|
||||
"\n",
|
||||
"X_with_bias = np.c_[np.ones([len(X), 1]), X] # Add column of ones for theta intercept term\n",
|
||||
"alpha = 0.1\n",
|
||||
"iterations=1500\n",
|
||||
"\n",
|
||||
"print(X.shape)\n",
|
||||
"\n",
|
||||
"# NOTE: If ValueError: all input arrays must have the same shape appears then you may have run this cel multiple times\n",
|
||||
"# which will have added multiple collumns of ones to the matrix X"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 70,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Setup our proportions\n",
|
||||
"\n",
|
||||
"test_ratio = .2\n",
|
||||
"val_ratio = .2\n",
|
||||
"total_size = len(X)\n",
|
||||
"\n",
|
||||
"# Calculate size of our splits\n",
|
||||
"\n",
|
||||
"test_size = int(test_ratio*total_size)\n",
|
||||
"val_size = int(val_ratio*total_size)\n",
|
||||
"train_size = total_size - test_size - val_size\n",
|
||||
"\n",
|
||||
"# Split our data\n",
|
||||
"\n",
|
||||
"rnd_indices = np.random.permutation(total_size) # Shuffle our input matrix\n",
|
||||
"\n",
|
||||
"X_train = X_with_bias[rnd_indices[:train_size]]\n",
|
||||
"y_train = y[rnd_indices[:train_size]]\n",
|
||||
"X_valid = X_with_bias[rnd_indices[train_size:-test_size]]\n",
|
||||
"y_valid = y[rnd_indices[train_size:-test_size]]\n",
|
||||
"X_test = X_with_bias[rnd_indices[-test_size:]]\n",
|
||||
"y_test = y[rnd_indices[-test_size:]]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 71,
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(90, 3)\n",
|
||||
"(30, 2)\n",
|
||||
"(30, 3)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(X_train.shape)\n",
|
||||
"print(X_val.shape)\n",
|
||||
"print(X_test.shape)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 72,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def to_one_hot(y):\n",
|
||||
" n_classes = y.max() + 1\n",
|
||||
" m = len(y)\n",
|
||||
" Y_one_hot = np.zeros((m, n_classes)) # Setup zero matrix with m rows and a column for each class\n",
|
||||
" Y_one_hot[np.arange(m), y] = 1 # Fill in ones\n",
|
||||
" return Y_one_hot"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 73,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"array([2, 2, 2, 0, 0, 0, 1, 2, 0, 2])"
|
||||
]
|
||||
},
|
||||
"execution_count": 73,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"y_train[:10]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 74,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"array([[0., 0., 1.],\n",
|
||||
" [0., 0., 1.],\n",
|
||||
" [0., 0., 1.],\n",
|
||||
" [1., 0., 0.],\n",
|
||||
" [1., 0., 0.],\n",
|
||||
" [1., 0., 0.],\n",
|
||||
" [0., 1., 0.],\n",
|
||||
" [0., 0., 1.],\n",
|
||||
" [1., 0., 0.],\n",
|
||||
" [0., 0., 1.]])"
|
||||
]
|
||||
},
|
||||
"execution_count": 74,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"to_one_hot(y_train[:10])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 75,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"Y_train_one_hot = to_one_hot(y_train)\n",
|
||||
"Y_test_one_hot = to_one_hot(y_test)\n",
|
||||
"Y_val_one_hot = to_one_hot(y_val)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 76,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Softmax function = exp(X) / (sum of exp(X))\n",
|
||||
"\n",
|
||||
"def softmax(logits):\n",
|
||||
" exps = np.exp(logits)\n",
|
||||
" exp_sums = np.sum(exps, axis=1, keepdims=True)\n",
|
||||
" return exps / exp_sums"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 82,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"n_inputs = X_train.shape[1] # Number of features\n",
|
||||
"n_outputs = len(np.unique(y_train)) # 3 uniqure values which will each be a possible output"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 80,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"0 1.4567897105648775\n",
|
||||
"500 0.7451993577978241\n",
|
||||
"1000 0.6279369677273878\n",
|
||||
"1500 0.5572702696067121\n",
|
||||
"2000 0.5111859948576022\n",
|
||||
"2500 0.47856473219026296\n",
|
||||
"3000 0.45387932862540925\n",
|
||||
"3500 0.43422780377165426\n",
|
||||
"4000 0.41797875623202274\n",
|
||||
"4500 0.4041537521442775\n",
|
||||
"5000 0.39213163561158126\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"eta = 0.01\n",
|
||||
"n_iterations = 5001\n",
|
||||
"m = len(X_train)\n",
|
||||
"epsilon = 1e-7\n",
|
||||
"\n",
|
||||
"Theta = np.random.randn(n_inputs, n_outputs)\n",
|
||||
"\n",
|
||||
"# Cycle through set to apply batch gradient descent\n",
|
||||
"\n",
|
||||
"for iteration in range(n_iterations):\n",
|
||||
" logits = X_train.dot(Theta) # Logits which are raw predictions from applying X to Theta\n",
|
||||
" p_hat = softmax(logits) # Apply softmax to logits to get our probabilities\n",
|
||||
" loss = -np.mean(np.sum(Y_train_one_hot * np.log(p_hat + epsilon), axis=1)) # Compute loss function\n",
|
||||
" error = p_hat - Y_train_one_hot # Compute error \n",
|
||||
" if iteration % 500 == 0:\n",
|
||||
" print(iteration, loss)\n",
|
||||
" Grad = 1/m * X_train.T.dot(error)\n",
|
||||
" Theta = Theta - eta * Grad\n",
|
||||
" "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 81,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"array([[ 3.61613128, 0.06856255, -2.86225561],\n",
|
||||
" [-0.2597962 , 0.80558911, 0.70553675],\n",
|
||||
" [-0.90831271, 0.18903751, 2.43558706]])"
|
||||
]
|
||||
},
|
||||
"execution_count": 81,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"Theta"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 87,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.9666666666666667"
|
||||
]
|
||||
},
|
||||
"execution_count": 87,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Predictions\n",
|
||||
"\n",
|
||||
"logits = X_valid.dot(Theta)\n",
|
||||
"p_hat = softmax(logits)\n",
|
||||
"y_pred = np.argmax(p_hat, axis=1)\n",
|
||||
"\n",
|
||||
"accuracy_score = np.mean(y_pred == y_valid)\n",
|
||||
"accuracy_score"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
|
|
@ -0,0 +1,521 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"from matplotlib import pyplot as plt\n",
|
||||
"import os\n",
|
||||
"from sklearn.datasets import fetch_openml\n",
|
||||
"from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier\n",
|
||||
"from sklearn.svm import LinearSVC\n",
|
||||
"from sklearn.metrics import accuracy_score\n",
|
||||
"from sklearn.preprocessing import normalize"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Exercise 8**\n",
|
||||
"\n",
|
||||
"Create hard/soft voting ensemble on mnist"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"mnist = fetch_openml('mnist_784', version=1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"dict_keys(['data', 'target', 'frame', 'feature_names', 'target_names', 'DESCR', 'details', 'categories', 'url'])"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"mnist.keys()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"(70000, 784)"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"X, y = mnist['data'], mnist['target']\n",
|
||||
"X.shape"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Split into train, val, test sets of size 50k, 10k, 10k\n",
|
||||
"\n",
|
||||
"X_train = X[:50000]\n",
|
||||
"y_train = y[:50000]\n",
|
||||
"X_val = X[50000:60000]\n",
|
||||
"y_val = y[50000:60000]\n",
|
||||
"X_test = X[60000:]\n",
|
||||
"y_test = y[60000:]\n",
|
||||
"\n",
|
||||
"# Normalize features\n",
|
||||
"\n",
|
||||
"X_train /= 255.0\n",
|
||||
"X_val /= 255.0\n",
|
||||
"X_test /= 255.0"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"1.0\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(X_test.max())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Training our RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None,\n",
|
||||
" criterion='gini', max_depth=None, max_features='auto',\n",
|
||||
" max_leaf_nodes=None, max_samples=None,\n",
|
||||
" min_impurity_decrease=0.0, min_impurity_split=None,\n",
|
||||
" min_samples_leaf=1, min_samples_split=2,\n",
|
||||
" min_weight_fraction_leaf=0.0, n_estimators=100,\n",
|
||||
" n_jobs=None, oob_score=False, random_state=None,\n",
|
||||
" verbose=0, warm_start=False)\n",
|
||||
"Training our ExtraTreesClassifier(bootstrap=False, ccp_alpha=0.0, class_weight=None,\n",
|
||||
" criterion='gini', max_depth=None, max_features='auto',\n",
|
||||
" max_leaf_nodes=None, max_samples=None,\n",
|
||||
" min_impurity_decrease=0.0, min_impurity_split=None,\n",
|
||||
" min_samples_leaf=1, min_samples_split=2,\n",
|
||||
" min_weight_fraction_leaf=0.0, n_estimators=100,\n",
|
||||
" n_jobs=None, oob_score=False, random_state=None, verbose=0,\n",
|
||||
" warm_start=False)\n",
|
||||
"Training our LinearSVC(C=1.0, class_weight=None, dual=True, fit_intercept=True,\n",
|
||||
" intercept_scaling=1, loss='squared_hinge', max_iter=1000,\n",
|
||||
" multi_class='ovr', penalty='l2', random_state=None, tol=0.0001,\n",
|
||||
" verbose=0)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"c:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\sklearn\\svm\\_base.py:947: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.\n",
|
||||
" \"the number of iterations.\", ConvergenceWarning)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"rfc = RandomForestClassifier()\n",
|
||||
"etc = ExtraTreesClassifier()\n",
|
||||
"svc = LinearSVC()\n",
|
||||
"\n",
|
||||
"classifiers = [rfc, etc, svc]\n",
|
||||
"scores = []\n",
|
||||
"\n",
|
||||
"# Fit each classifier to the training set and predict on X_val\n",
|
||||
"for clf in classifiers:\n",
|
||||
" print('Training our ', clf)\n",
|
||||
" clf.fit(X_train, y_train)\n",
|
||||
" score = clf.score(X_val, y_val)\n",
|
||||
" scores.append(score)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[0.9719, 0.9741, 0.9208]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(scores)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"c:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\sklearn\\svm\\_base.py:947: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.\n",
|
||||
" \"the number of iterations.\", ConvergenceWarning)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"VotingClassifier(estimators=[('rf',\n",
|
||||
" RandomForestClassifier(bootstrap=True,\n",
|
||||
" ccp_alpha=0.0,\n",
|
||||
" class_weight=None,\n",
|
||||
" criterion='gini',\n",
|
||||
" max_depth=None,\n",
|
||||
" max_features='auto',\n",
|
||||
" max_leaf_nodes=None,\n",
|
||||
" max_samples=None,\n",
|
||||
" min_impurity_decrease=0.0,\n",
|
||||
" min_impurity_split=None,\n",
|
||||
" min_samples_leaf=1,\n",
|
||||
" min_samples_split=2,\n",
|
||||
" min_weight_fraction_leaf=0.0,\n",
|
||||
" n_estimators=100,\n",
|
||||
" n_jobs=None,\n",
|
||||
" oob_score...\n",
|
||||
" n_estimators=100,\n",
|
||||
" n_jobs=None, oob_score=False,\n",
|
||||
" random_state=None, verbose=0,\n",
|
||||
" warm_start=False)),\n",
|
||||
" ('sv',\n",
|
||||
" LinearSVC(C=1.0, class_weight=None, dual=True,\n",
|
||||
" fit_intercept=True, intercept_scaling=1,\n",
|
||||
" loss='squared_hinge', max_iter=1000,\n",
|
||||
" multi_class='ovr', penalty='l2',\n",
|
||||
" random_state=None, tol=0.0001,\n",
|
||||
" verbose=0))],\n",
|
||||
" flatten_transform=True, n_jobs=None, voting='hard',\n",
|
||||
" weights=None)"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from sklearn.ensemble import VotingClassifier\n",
|
||||
"\n",
|
||||
"# Hard vote ensmeble\n",
|
||||
"voting_clf = VotingClassifier(\n",
|
||||
" estimators=[('rf', rfc), ('et', etc), ('sv', svc)],\n",
|
||||
" voting='hard'\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"voting_clf.fit(X_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.9719"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"voting_clf.score(X_val, y_val)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Try without SVC\n",
|
||||
"\n",
|
||||
"del voting_clf.estimators_[2]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.9732"
|
||||
]
|
||||
},
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"voting_clf.score(X_val, y_val)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.9752"
|
||||
]
|
||||
},
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Set to soft voting and check if better\n",
|
||||
"\n",
|
||||
"voting_clf.voting='soft'\n",
|
||||
"\n",
|
||||
"voting_clf.score(X_val, y_val)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.9707"
|
||||
]
|
||||
},
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Check on Test Set\n",
|
||||
"\n",
|
||||
"voting_clf.score(X_test, y_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Exercise 9**\n",
|
||||
"\n",
|
||||
"train a stacking ensemble on our previous classifiers"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Round up our predictions\n",
|
||||
"\n",
|
||||
"X_val_predictions = np.empty((len(X_val), len(classifiers)), dtype=np.float32)\n",
|
||||
"\n",
|
||||
"for index, clf in enumerate(classifiers):\n",
|
||||
" X_val_predictions[:, index] = clf.predict(X_val)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[[3. 3. 3.]\n",
|
||||
" [8. 8. 8.]\n",
|
||||
" [6. 6. 6.]\n",
|
||||
" ...\n",
|
||||
" [5. 5. 5.]\n",
|
||||
" [6. 6. 6.]\n",
|
||||
" [8. 8. 8.]]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(X_val_predictions)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 32,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None,\n",
|
||||
" criterion='gini', max_depth=None, max_features='auto',\n",
|
||||
" max_leaf_nodes=None, max_samples=None,\n",
|
||||
" min_impurity_decrease=0.0, min_impurity_split=None,\n",
|
||||
" min_samples_leaf=1, min_samples_split=2,\n",
|
||||
" min_weight_fraction_leaf=0.0, n_estimators=200,\n",
|
||||
" n_jobs=None, oob_score=True, random_state=None,\n",
|
||||
" verbose=0, warm_start=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 32,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Train a classifier which will take as input our predictions matrix\n",
|
||||
"blender = RandomForestClassifier(n_estimators=200, oob_score=True)\n",
|
||||
"blender.fit(X_val_predictions, y_val)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 33,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.9727"
|
||||
]
|
||||
},
|
||||
"execution_count": 33,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Check our out of bag score to get an idea of accuracy\n",
|
||||
"blender.oob_score_"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 35,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Round up predictions for X_test\n",
|
||||
"X_test_predictions = np.empty((len(X_val), len(classifiers)), dtype=np.float32)\n",
|
||||
"\n",
|
||||
"for index, clf in enumerate(classifiers):\n",
|
||||
" X_test_predictions[:, index] = clf.predict(X_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 36,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Use our blender to predict based on our predictions matrix\n",
|
||||
"y_pred = blender.predict(X_test_predictions)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 38,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.968"
|
||||
]
|
||||
},
|
||||
"execution_count": 38,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"accuracy_score(y_pred, y_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
|
|
@ -0,0 +1,521 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"from matplotlib import pyplot as plt\n",
|
||||
"import os\n",
|
||||
"from sklearn.datasets import fetch_openml\n",
|
||||
"from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier\n",
|
||||
"from sklearn.svm import LinearSVC\n",
|
||||
"from sklearn.metrics import accuracy_score\n",
|
||||
"from sklearn.preprocessing import normalize"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Exercise 8**\n",
|
||||
"\n",
|
||||
"Create hard/soft voting ensemble on mnist"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"mnist = fetch_openml('mnist_784', version=1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"dict_keys(['data', 'target', 'frame', 'feature_names', 'target_names', 'DESCR', 'details', 'categories', 'url'])"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"mnist.keys()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"(70000, 784)"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"X, y = mnist['data'], mnist['target']\n",
|
||||
"X.shape"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Split into train, val, test sets of size 50k, 10k, 10k\n",
|
||||
"\n",
|
||||
"X_train = X[:50000]\n",
|
||||
"y_train = y[:50000]\n",
|
||||
"X_val = X[50000:60000]\n",
|
||||
"y_val = y[50000:60000]\n",
|
||||
"X_test = X[60000:]\n",
|
||||
"y_test = y[60000:]\n",
|
||||
"\n",
|
||||
"# Normalize features\n",
|
||||
"\n",
|
||||
"X_train /= 255.0\n",
|
||||
"X_val /= 255.0\n",
|
||||
"X_test /= 255.0"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"1.0\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(X_test.max())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Training our RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None,\n",
|
||||
" criterion='gini', max_depth=None, max_features='auto',\n",
|
||||
" max_leaf_nodes=None, max_samples=None,\n",
|
||||
" min_impurity_decrease=0.0, min_impurity_split=None,\n",
|
||||
" min_samples_leaf=1, min_samples_split=2,\n",
|
||||
" min_weight_fraction_leaf=0.0, n_estimators=100,\n",
|
||||
" n_jobs=None, oob_score=False, random_state=None,\n",
|
||||
" verbose=0, warm_start=False)\n",
|
||||
"Training our ExtraTreesClassifier(bootstrap=False, ccp_alpha=0.0, class_weight=None,\n",
|
||||
" criterion='gini', max_depth=None, max_features='auto',\n",
|
||||
" max_leaf_nodes=None, max_samples=None,\n",
|
||||
" min_impurity_decrease=0.0, min_impurity_split=None,\n",
|
||||
" min_samples_leaf=1, min_samples_split=2,\n",
|
||||
" min_weight_fraction_leaf=0.0, n_estimators=100,\n",
|
||||
" n_jobs=None, oob_score=False, random_state=None, verbose=0,\n",
|
||||
" warm_start=False)\n",
|
||||
"Training our LinearSVC(C=1.0, class_weight=None, dual=True, fit_intercept=True,\n",
|
||||
" intercept_scaling=1, loss='squared_hinge', max_iter=1000,\n",
|
||||
" multi_class='ovr', penalty='l2', random_state=None, tol=0.0001,\n",
|
||||
" verbose=0)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"c:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\sklearn\\svm\\_base.py:947: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.\n",
|
||||
" \"the number of iterations.\", ConvergenceWarning)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"rfc = RandomForestClassifier()\n",
|
||||
"etc = ExtraTreesClassifier()\n",
|
||||
"svc = LinearSVC()\n",
|
||||
"\n",
|
||||
"classifiers = [rfc, etc, svc]\n",
|
||||
"scores = []\n",
|
||||
"\n",
|
||||
"# Fit each classifier to the training set and predict on X_val\n",
|
||||
"for clf in classifiers:\n",
|
||||
" print('Training our ', clf)\n",
|
||||
" clf.fit(X_train, y_train)\n",
|
||||
" score = clf.score(X_val, y_val)\n",
|
||||
" scores.append(score)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[0.9719, 0.9741, 0.9208]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(scores)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"c:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\sklearn\\svm\\_base.py:947: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.\n",
|
||||
" \"the number of iterations.\", ConvergenceWarning)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"VotingClassifier(estimators=[('rf',\n",
|
||||
" RandomForestClassifier(bootstrap=True,\n",
|
||||
" ccp_alpha=0.0,\n",
|
||||
" class_weight=None,\n",
|
||||
" criterion='gini',\n",
|
||||
" max_depth=None,\n",
|
||||
" max_features='auto',\n",
|
||||
" max_leaf_nodes=None,\n",
|
||||
" max_samples=None,\n",
|
||||
" min_impurity_decrease=0.0,\n",
|
||||
" min_impurity_split=None,\n",
|
||||
" min_samples_leaf=1,\n",
|
||||
" min_samples_split=2,\n",
|
||||
" min_weight_fraction_leaf=0.0,\n",
|
||||
" n_estimators=100,\n",
|
||||
" n_jobs=None,\n",
|
||||
" oob_score...\n",
|
||||
" n_estimators=100,\n",
|
||||
" n_jobs=None, oob_score=False,\n",
|
||||
" random_state=None, verbose=0,\n",
|
||||
" warm_start=False)),\n",
|
||||
" ('sv',\n",
|
||||
" LinearSVC(C=1.0, class_weight=None, dual=True,\n",
|
||||
" fit_intercept=True, intercept_scaling=1,\n",
|
||||
" loss='squared_hinge', max_iter=1000,\n",
|
||||
" multi_class='ovr', penalty='l2',\n",
|
||||
" random_state=None, tol=0.0001,\n",
|
||||
" verbose=0))],\n",
|
||||
" flatten_transform=True, n_jobs=None, voting='hard',\n",
|
||||
" weights=None)"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from sklearn.ensemble import VotingClassifier\n",
|
||||
"\n",
|
||||
"# Hard vote ensmeble\n",
|
||||
"voting_clf = VotingClassifier(\n",
|
||||
" estimators=[('rf', rfc), ('et', etc), ('sv', svc)],\n",
|
||||
" voting='hard'\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"voting_clf.fit(X_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.9719"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"voting_clf.score(X_val, y_val)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Try without SVC\n",
|
||||
"\n",
|
||||
"del voting_clf.estimators_[2]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.9732"
|
||||
]
|
||||
},
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"voting_clf.score(X_val, y_val)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.9752"
|
||||
]
|
||||
},
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Set to soft voting and check if better\n",
|
||||
"\n",
|
||||
"voting_clf.voting='soft'\n",
|
||||
"\n",
|
||||
"voting_clf.score(X_val, y_val)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.9707"
|
||||
]
|
||||
},
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Check on Test Set\n",
|
||||
"\n",
|
||||
"voting_clf.score(X_test, y_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Exercise 9**\n",
|
||||
"\n",
|
||||
"train a stacking ensemble on our previous classifiers"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Round up our predictions\n",
|
||||
"\n",
|
||||
"X_val_predictions = np.empty((len(X_val), len(classifiers)), dtype=np.float32)\n",
|
||||
"\n",
|
||||
"for index, clf in enumerate(classifiers):\n",
|
||||
" X_val_predictions[:, index] = clf.predict(X_val)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[[3. 3. 3.]\n",
|
||||
" [8. 8. 8.]\n",
|
||||
" [6. 6. 6.]\n",
|
||||
" ...\n",
|
||||
" [5. 5. 5.]\n",
|
||||
" [6. 6. 6.]\n",
|
||||
" [8. 8. 8.]]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(X_val_predictions)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 32,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None,\n",
|
||||
" criterion='gini', max_depth=None, max_features='auto',\n",
|
||||
" max_leaf_nodes=None, max_samples=None,\n",
|
||||
" min_impurity_decrease=0.0, min_impurity_split=None,\n",
|
||||
" min_samples_leaf=1, min_samples_split=2,\n",
|
||||
" min_weight_fraction_leaf=0.0, n_estimators=200,\n",
|
||||
" n_jobs=None, oob_score=True, random_state=None,\n",
|
||||
" verbose=0, warm_start=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 32,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Train a classifier which will take as input our predictions matrix\n",
|
||||
"blender = RandomForestClassifier(n_estimators=200, oob_score=True)\n",
|
||||
"blender.fit(X_val_predictions, y_val)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 33,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.9727"
|
||||
]
|
||||
},
|
||||
"execution_count": 33,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Check our out of bag score to get an idea of accuracy\n",
|
||||
"blender.oob_score_"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 35,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Round up predictions for X_test\n",
|
||||
"X_test_predictions = np.empty((len(X_val), len(classifiers)), dtype=np.float32)\n",
|
||||
"\n",
|
||||
"for index, clf in enumerate(classifiers):\n",
|
||||
" X_test_predictions[:, index] = clf.predict(X_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 36,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Use our blender to predict based on our predictions matrix\n",
|
||||
"y_pred = blender.predict(X_test_predictions)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 38,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0.968"
|
||||
]
|
||||
},
|
||||
"execution_count": 38,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"accuracy_score(y_pred, y_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
Loading…
Reference in New Issue